Wafer factory batch production scheduling method, equipment, medium and product

Abstract

The embodiment of the invention relates to the technical field of wafer production scheduling, and discloses a wafer factory batch production scheduling method and device, a medium and a product. Acquiring batch information, equipment state information and equipment maintenance information of wafers to be processed; determining an objective function of the scheduling model, wherein the objective function includes minimizing processing time of equipment, minimizing idle time of the equipment, minimizing use of replacement slices, equipment load balancing and high-priority batches; determining constraint conditions of the scheduling model, wherein the constraint conditions comprise single-equipment continuous processing limitation of each wafer batch, batch grouping requirements based on the same process formula, and cleaning requirements after equipment batch processing; and according to the wafer batch information to be processed, the equipment state information, the equipment maintenance information and the scheduling model, generating a scheduling scheme and outputting a Gantt chart. The technical problem that wafer scheduling depends on manual scheduling can be at least solved.

Description

Technical Field

[0001] The present application relates to the technical field of wafer production scheduling, and in particular to a wafer fab batch production scheduling method, equipment, medium and product. Background Art

[0002] With the rapid development of the semiconductor industry, the large-scale production of 12-inch wafer fabs has become a key means to increase production capacity and reduce costs. Compared with 8-inch wafers, 12-inch wafers can produce more chips on the same wafer, thereby significantly reducing the production cost of a single chip. This scale advantage not only improves production efficiency, but also promotes the overall progress of the semiconductor industry, especially in China, where the construction and capacity expansion of 12-inch wafer fabs have become an important driving force for the development of the domestic semiconductor industry.

[0003] In the wafer manufacturing process, the production process includes multiple process steps such as diffusion, cleaning, photolithography, and etching. The precise control of each step is crucial to product performance. The diffusion process is a key step in forming semiconductor devices by diffusing impurities into silicon wafers under high temperature conditions to form PN junctions, while the cleaning process is used to remove impurities on the surface of silicon wafers to ensure the smooth progress of subsequent processes. In order to ensure the smooth progress of these key processes, batch scheduling of batch production equipment becomes particularly important.

[0004] Traditional production scheduling methods usually rely on manual operations, which are mainly limited by the completion time of the previous process, are inefficient and easily cause production delays. Existing batch scheduling algorithms often face problems of insufficient efficiency and untimely response when dealing with large-scale and changing production environments. In addition, during the production process, equipment may be unavailable due to preventive maintenance (PM) or unexpected downtime (Down), further increasing the complexity of scheduling. Summary of the invention

[0005] One purpose of the present application is to provide a wafer fab batch production scheduling method, equipment, medium and product, at least to solve the technical problem that wafer scheduling relies on manual scheduling.

[0006] To achieve the above objectives, some embodiments of the present application provide the following aspects:

[0007] In the first aspect, some embodiments of the present application also provide a wafer factory batch production scheduling method, including obtaining wafer batch information to be processed, equipment status information and equipment maintenance information; determining the objective function of the scheduling model, the objective function includes minimizing the processing time of the equipment, minimizing the idle time of the equipment, minimizing the use of replacement wafers, equipment load balancing and high-priority batches; determining the constraints of the scheduling model, the constraints include single-device continuous processing restrictions for each wafer batch, batch requirements based on the same process recipe, and cleaning requirements after equipment batch processing; based on the wafer batch information to be processed, the equipment status information and equipment maintenance information, the scheduling model generates a scheduling plan and outputs a Gantt chart.

[0008] In a second aspect, some embodiments of the present application further provide an electronic device, comprising: one or more processors; and a memory storing computer program instructions, wherein the computer program instructions, when executed, cause the processor to perform the steps of the method described above.

[0009] In a third aspect, some embodiments of the present application further provide a computer-readable medium having computer program instructions stored thereon, wherein the computer program instructions can be executed by a processor to implement the method as described above.

[0010] In a fourth aspect, some embodiments of the present application further provide a computer program product, comprising a computer program / instruction, which implements the steps of the method described above when executed by a processor.

[0011] Compared with the related art, the solution provided in the embodiment of the present application significantly improves the production efficiency and equipment utilization of the wafer fab through the automated batch scheduling algorithm, reduces the reliance on manual scheduling and the scheduling inaccuracy caused by human factors. The production cost is further reduced by optimizing the processing time of the equipment, reducing the idle time of the equipment, and controlling the use of replacement wafers. At the same time, it can be dynamically adjusted according to various factors such as equipment status and batch priority to ensure the priority processing of emergency batches and the flexibility of production scheduling to meet complex and changing production needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0013] Figure 1 A schematic diagram of a process flow of a wafer fab batch production scheduling method provided according to an embodiment of the present application;

[0014] Figure 2 A schematic diagram of a wafer batch provided according to an embodiment of the present application;

[0015] Figure 3 A schematic diagram of wafer batch processing provided according to an embodiment of the present application;

[0016] Figure 4 A Gantt chart showing wafer production according to an embodiment of the present application;

[0017] Figure 5 A schematic diagram of a Gantt chart of a scheduling result provided according to an embodiment of the present application;

[0018] Figure 6 The present invention is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0020] The following terms are used in this article.

[0021] 1) diffusion: diffusion process;

[0022] 2) Wet: cleaning process;

[0023] 3) Wafer: wafer;

[0024] 4) lot: the unit for storing wafers;

[0025] 5) dummywafer: substitute wafer;

[0026] 6) purge: furnace tube cleaning;

[0027] 7) PM: Preventive Maintenance. To ensure the stability and reliability of the equipment, preventive maintenance should be performed on the equipment regularly. During PM, the equipment will not be processed, and production should avoid scheduling during this period. PM frequency: once a week or once a month;

[0028] 8) Down: The equipment is in the Down state and does not perform processing;

[0029] 9) idle: the machine has no processing tasks and is idle;

[0030] 10) loadport: wafer loader;

[0031] 11) recipe: processing recipe;

[0032] 12) batch: diffusion area batch;

[0033] 13) bench: wet area group batch.

[0034] The economies of scale of 12-inch wafer fabs are significant. Compared with 8-inch wafers, they can produce more chips on the same wafer, thereby reducing the cost of a single chip. This scale advantage not only improves production efficiency, but also makes semiconductor products more affordable. 12-inch wafer fabs account for a considerable proportion of global wafer fabs, and this proportion continues to rise with the development of technology and the growth of market demand. Especially in China, the construction and capacity expansion of 12-inch wafer fabs are becoming an important force in promoting the development of the semiconductor industry.

[0035] The semiconductor production process includes multiple stages, such as diffusion, lithography, etching, cleaning, etc., and each stage requires precise control and optimization. Among them, the batch scheduling algorithm of batch production equipment is one of the key technologies to ensure production efficiency and product quality. In particular, batch and bench grouping operations are required in the diffusion and cleaning (wet) areas, and these process steps have a decisive impact on the performance of the final product.

[0036] Importance of semiconductor diffusion process: Diffusion process is a key step in semiconductor manufacturing for changing the surface characteristics of silicon wafers. By doping impurity elements into silicon wafers at high temperatures, regions with different electrical properties can be formed, such as PN junctions, which are the basis of semiconductor devices. The diffusion process requires precise control of temperature, time, atmosphere and impurity concentration to ensure that the uniformity and depth of the diffusion layer meet the design requirements.

[0037] Necessity of cleaning process: Cleaning is another important step in semiconductor production. It is used to remove impurities and residues on the surface of silicon wafers to prevent them from affecting subsequent process steps. The cleaning process requires the use of specific chemical solutions and auxiliary cleaning by physical methods such as ultrasound and sputtering to ensure the cleanliness of the silicon wafer surface.

[0038] In the traditional scheduling practice of semiconductor wafer manufacturing, manual operation and decision-making are usually relied on. This method is largely limited by the completion time of the previous processing step. Due to the lack of an automated batching mechanism, it is often necessary to wait for a batch of wafers (lot) with the same process recipe to be fully processed before batch production can be started. This practice not only increases waiting time and reduces production efficiency, but also leads to a large waste of human resources. In addition, manual scheduling is easily interfered by human factors when dealing with large-scale, multi-variable production tasks, and it is difficult to ensure the consistency and accuracy of scheduling. With the rapid development of the semiconductor industry, the complexity and variability of production needs are increasing, and traditional manual scheduling methods have been unable to meet the needs of modern production.

[0039] With the rapid development of semiconductor technology, wafer production needs have become more diversified and personalized, which requires the scheduling system to not only be able to handle large-scale production data, but also be able to flexibly respond to changes in production needs. Existing scheduling algorithms are often inefficient when dealing with complex and dynamic production environments, making it difficult to achieve real-time optimization and adjustment.

[0040] At the same time, the wafer production scheduling problem is a typical multi-constraint and multi-objective problem. Wafer production scheduling is affected by machine equipment, wafer priority, etc. In the actual production process, the machine may also experience unexpected situations such as PM or downtime. For some high-urgency lot, they should be prioritized for production scheduling. And in the batching process, it is necessary to use as few dummy wafers as possible to reduce economic costs. In addition, the purge process must also be considered.

[0041] In order to overcome these limitations, this application proposes a wafer fab batch production scheduling method, equipment, medium and product, which aims to reduce the reliance on manual scheduling and improve production efficiency and flexibility. By intelligently identifying and combining wafer batches with the same process requirements, optimizing the production process, reducing equipment conversion time, and combining advanced optimization technology, the automation and intelligence of production scheduling can be achieved. In this way, production efficiency can be significantly improved and production costs can be reduced.

[0042] First embodiment

[0043] The first embodiment of the present application relates to a wafer fab batch production scheduling method. Figure 1 As shown, the method may include the following steps:

[0044] S101, obtaining wafer batch information, equipment status information and equipment maintenance information to be processed;

[0045] S102, determining an objective function of a scheduling model, wherein the objective function includes minimizing a processing time of a device, minimizing an idle time of a device, minimizing the use of replacement sheets, balancing device loads, and high-priority batches;

[0046] S103, determining constraints of the scheduling model, wherein the constraints include a single-device continuous processing limit for each wafer batch, a batching requirement based on the same process recipe, and a cleaning requirement after the equipment batch is processed;

[0047] S104, according to the wafer batch information to be processed, the equipment status information and the equipment maintenance information, the scheduling model generates a scheduling plan and outputs a Gantt chart.

[0048] The following is a detailed description of each of the above steps.

[0049] For step S101, various types of information related to production scheduling are obtained through the factory database. Specifically including: wafer batch information, extracting detailed information of the wafer batch to be processed, including the arrival time of the wafer batch, the number of wafers in each batch, the process recipe required for processing, and the priority of the wafer batch, etc. Equipment status information, obtaining the real-time status of each production equipment, including whether the equipment is idle, in processing, or down due to a fault, or unavailable due to regular preventive maintenance (PM). Equipment maintenance information, obtaining equipment maintenance plan information, including the schedule of preventive maintenance, to ensure that when scheduling, the unavailable period of the equipment can be reasonably avoided to avoid interfering with the production process.

[0050] For step S102, an objective function of the scheduling model is constructed according to a preset optimization target. The objective function is designed to optimize the production efficiency and resource utilization of the wafer fab, and mainly includes the following optimization targets:

[0051] Minimize the processing time of the equipment. Reduce the actual processing time of each equipment by optimizing the schedule, ensure that the equipment can operate at the highest efficiency, speed up batch production, and shorten the overall production cycle.

[0052] Minimize the idle time of equipment by reasonably arranging the processing sequence of batches, reducing the idle period of equipment, avoiding long-term idleness of equipment when switching batches or waiting for processes, and improving equipment utilization.

[0053] Minimize the use of dummy wafers. In the diffusion process area, the use of dummy wafers is usually to ensure that the batch quantity meets the minimum processing requirements of the equipment. The batch group will be optimized to minimize the use of dummy wafers, thereby reducing resource waste in the production process and reducing production costs.

[0054] Equipment load balancing, by reasonably allocating batches to each device, avoids overloading some devices while leaving others idle. This goal ensures even use of equipment resources and prevents failures or reduced efficiency caused by long-term overloading of some devices.

[0055] Prioritize high-priority batches (super hot lot), dynamically adjust the scheduling strategy according to the priority of the batch, and prioritize the production of wafer batches with high priority or urgent orders to ensure that these batches can be processed on time to meet the urgent needs of customers.

[0056] For step S103, in order to ensure the rationality and practical operability of the scheduling scheme, a series of constraints are set for the scheduling model. These constraints stipulate the basic rules that must be followed in the production process, including the following items:

[0057] Single-device continuous processing limitation: Each wafer batch must be processed continuously on the same device to avoid switching devices during the processing process, so as to prevent delays, misoperations and unnecessary production interruptions that may occur when switching devices, ensuring the continuity and stability of the processing process.

[0058] Based on the batching requirements of the same process recipe, wafer batches with the same processing recipe need to be batch processed on the same equipment. By processing wafer batches with the same recipe at the same time, the frequency of equipment switching can be reduced and the efficiency of batch processing can be improved.

[0059] Equipment cleaning requirements (purge): The equipment needs to be cleaned after completing a predetermined number of batches. During the cleaning process, the equipment will suspend production and processing. The cleaning time of the equipment must be reasonably arranged during scheduling to ensure that the cleaning operation does not affect the overall production progress and prevent production quality problems caused by insufficient cleaning.

[0060] For step S104, after determining the objective function and constraints of the scheduling model, a scheduling plan is generated. Based on various factors such as wafer batches, equipment status, and equipment maintenance, an optimization algorithm is used to generate a specific production scheduling plan, which is presented in the form of a Gantt chart for intuitive viewing and adjustment by managers. The detailed process of this step is as follows:

[0061] First, the previously acquired wafer batch information (including arrival time, priority, process recipe, etc.), equipment status information (such as whether the equipment is idle, processing, downtime or preventive maintenance status), and equipment maintenance information (preventive maintenance time plan, cleaning requirements, etc.) are integrated and used as input data for scheduling. The accuracy and timeliness of all data directly affect the rationality of the final scheduling plan.

[0062] The integrated data is processed using the set optimization algorithm. The algorithm automatically generates the optimal scheduling plan based on the objective function and constraints. Specifically: according to the priority of each wafer batch and its arrival time, appropriate equipment is assigned, and high-priority batches (super hot lot) are prioritized for processing; according to the current status of the equipment, each batch is ensured to be assigned only to idle and qualified equipment to avoid equipment being assigned tasks during downtime or preventive maintenance; considering the cleaning needs of the equipment, the cleaning time between batches is reasonably arranged to ensure that the equipment is cleaned after a predetermined number of batches to prevent contamination caused by excessive processing; at the same time, ensure that the load of the equipment is balanced, and try to avoid excessive use or long-term idleness of individual equipment, thereby improving the overall equipment utilization rate.

[0063] After the algorithm is processed, a scheduling plan is generated, which lists in detail the key information of each wafer batch, including the processing equipment, processing start and end time, cleaning operation time and frequency, etc. The scheduling plan ensures that all batches can be processed within the specified time while avoiding equipment conflicts and downtime problems.

[0064] The generated scheduling plan is converted into a Gantt chart for intuitive viewing and analysis by managers. The Gantt chart is based on the timeline and shows the processing time period and progress of each wafer batch on different equipment. It also indicates the equipment's idle time, cleaning operation time, maintenance time, etc. Through the Gantt chart, managers can quickly understand the production schedule of each batch and the use of equipment, so as to have a comprehensive grasp of the production process.

[0065] The output of the Gantt chart not only makes it easy for managers to view the scheduling progress, but also allows them to make adjustments based on actual production conditions. If an emergency occurs, such as a sudden equipment shutdown or a new urgent batch that needs to be scheduled, managers can regenerate a new scheduling plan by adjusting the various task nodes on the Gantt chart. The optimization algorithm will automatically run again based on the new input data to ensure that the new scheduling plan also meets the objective function and constraints.

[0066] It is not difficult to find that compared with the related art, the solution provided in the embodiment of the present application has made innovative improvements to the batch strategy. Since the strategy can be dynamically adjusted according to production needs and equipment capabilities, the batch combination is more reasonable, which has the significant effect of optimizing the production process, improving equipment utilization and reducing production costs. Through the intelligent batch scheduling algorithm, production delays caused by equipment waiting or improper scheduling can be effectively reduced.

[0067] Second embodiment

[0068] The second embodiment of the present application relates to a wafer fab batch production scheduling method. The second implementation is an improvement on the first embodiment, and the specific improvements are:

[0069] For the diffusion and wet processes in semiconductor production, special production methods such as batch operation are required, such as Figure 2 As shown: Batch is mainly used for diffusion process. Wafer batches need to be processed at high temperature, so multiple wafer batches (lots) are loaded into the same diffusion furnace for processing at the same time. Each diffusion furnace usually has multiple batch positions, and a total of multiple batches of wafers are processed at the same time. These batches usually have the same processing recipe, such as the same doping requirements and temperature conditions. The combination of batches is based on the capacity of the equipment and the process compatibility between batches, ensuring that all wafer batches processed in the same batch run under the same process to improve production efficiency.

[0070] Bench groups are mainly used for cleaning processes, and each bench group usually includes fewer batches. The cleaning process has high requirements for batches, so bench groups usually only contain a small number of batches to ensure uniform and thorough cleaning. The batches in the bench group also need to have the same cleaning process recipe to avoid cross-contamination or incompatible process parameters that have a negative impact on the wafer.

[0071] According to the wafer batch information to be processed, batches with the same process recipe are selected for batch grouping. In the process of batch grouping, the number of batches that can be processed simultaneously is determined according to the capacity of the equipment, and the location of each batch is arranged reasonably. In order to improve the utilization rate of the equipment, the batches will be combined to the maximum capacity limit to reduce the idle time and the frequency of equipment cleaning. At the same time, in the process of batch grouping and bench grouping, the use of dummy wafers is minimized to reduce costs. After each batch or bench is processed, the equipment may need to be cleaned, and the appropriate cleaning time will be automatically arranged to ensure the normal operation of the equipment.

[0072] like Figure 3 As shown in the figure, the batch production process includes: batch binding. In the initial stage of production, batch binding is first performed based on the current wafer batch information to be processed. This stage involves selecting batches with the same processing recipe and process requirements, and binding them together to form a batch group. The binding process ensures that each batch can be processed under the same conditions in the subsequent processing, avoiding quality problems caused by process mismatch, taking into account equipment capacity, batch priority and process requirements, and ensuring the optimization of batching.

[0073] Production and processing, after the batching is completed and bound, enters the production and processing stage. In this stage, the bound batch groups are assigned to the designated equipment for processing. At this time, the equipment processes all bound batches at the same time according to the set process recipe (such as diffusion, cleaning, etc.). During this process, the equipment will perform high-temperature diffusion, chemical cleaning and other operations according to the process requirements to ensure that the wafer batch is processed according to the design specifications.

[0074] After the processing is completed, the equipment has completed all process treatments for this group of batches, and all wafer batches have met the set processing requirements. The equipment may perform a cleaning operation (purge) as needed to ensure that it remains clean before the next group of batches enters the equipment.

[0075] Batch unbinding, after the production and processing is completed, enter the batch unbinding stage. The batches that have been processed will be automatically released from the binding state so that they can enter the subsequent production process or outbound processing. After the batch is unbinded, the equipment will also return to the idle state, ready to receive a new batch group for the next round of processing.

[0076] It is not difficult to find that compared with the related art, the solution provided by the embodiment of the present application, for the batch processing process of the diffusion area and the cleaning area, can achieve efficient production scheduling and ensure the smooth operation of the wafer fab production line. Batch binding ensures that batches with the same process requirements are reasonably combined to maximize equipment utilization; production processing is the core of the entire process, ensuring that all bound batches are processed synchronously according to process requirements; after processing, the batch status is automatically tracked to ensure smooth production connection; batch unbinding reserves equipment resources for the processing of subsequent batches to maintain production continuity.

[0077] Third embodiment

[0078] The third embodiment of the present application relates to a wafer fab batch production scheduling method. The third implementation method is an improvement on the first embodiment, and the specific improvements are:

[0079] Obtain the data information of running lot, prepare lot, lot to be arranged, relevant data information of the machine, relevant data information of PM / Down machine, and other relevant information from the database.

[0080] The objective functions of the scheduling model include: 1) minimizing the machine processing time; 2) minimizing the machine idle time; 3) minimizing the number of dummy sheets used; 4) balancing the machine load; 5) scheduling as many lots as possible for processing; 6) giving priority to production and processing of lots with high priority; 7) other goals set by the user.

[0081] The constraints for determining the scheduling model include: 1) A lot can only be processed on one device, and the processing must be continuous and cannot be interrupted; 2) Only lots with the same recipe can be batched; 3) The number of lots in a batch is constrained; 4) Optional constraint: The number of lots with small numbers of wafers in a batch; 5) Optional constraint: The total number of wafers in the same batch; 6) Optional constraint: A machine needs to be purged after processing several batches, and the machine cannot be used for production during the purge; 7) Other batching constraints based on the characteristics of the machine and the requirements of the customer in actual production and processing; 8) The equipment must be able to produce and process after the set allowed processing time point; 9) The processing time of a lot cannot be earlier than its arrival time, and cannot be later than the time it arrives in this area (arrive time) + the maximum waiting time (queue time); 10) Run lot and prepare The processing machines, processing time and sequence of a lot are fixed and cannot be changed during scheduling; 11) When a machine is in PM or Down state, the equipment cannot perform any production processing or other operations; 12) For some lots with particularly high urgency (super hot lots), they will be prioritized for processing and scheduling.

[0082] The scheduling model generates a scheduling plan and outputs a Gantt chart including:

[0083] Get the information of the running lot (start processing time, end processing time). The running lot is the lot that is being processed on the equipment. The lot in this state has a fixed processing time and sequence, so there is no need to schedule it.

[0084] Get the information of prepare lot (start processing time, end processing time). Prepare lot is the lot that has entered the equipment and is preparing for processing. The lot in this state has fixed processing time and sequence, so it does not need to be scheduled.

[0085] Get the information of the lot to be queued (including its arrival time, maximum waiting time, queue time, set of optional processing machines, number of wafers, processing recipe, processing time, priority, and other relevant information).

[0086] Relevant information of the equipment (allowed processing time, maximum number of lots allowed in a batch, minimum number of lots allowed in a batch, number of batches allowed to be processed before purge).

[0087] PM / Down machine related information (equipment machine id, earliest start time, duration time, latest start time).

[0088] In the precision world of semiconductor manufacturing, every second counts. The processing time of diffusion and wet etching machines directly affects the throughput of the production line and the overall production cost. Shortening the processing time of these two steps can not only improve production efficiency and speed up the time to market, but also reduce production costs and improve the competitiveness of enterprises. In addition, the fast processing process also helps to reduce the defects that may be introduced by long processing, thereby improving the performance and reliability of the final product. At the same time, adding this indicator to the model can also ensure the close arrangement of lots on the machine, so that the scheduling results are more reasonable. The objective function is: Min Sum (machineEndTime).

[0089] Minimize the machine idle time to optimize the scheduling results and prevent unexplained machine idle time. The objective function is: Min Sum (machineIdleTime).

[0090] Optional goal: In the scheduling of the diffusion area, the total number of dummy wafers used is the least. In the scheduling management of the diffusion process area, we strive to minimize the number of virtual wafers used. This strategy aims to optimize resource allocation, reduce unnecessary production costs, and improve overall equipment utilization. By accurately controlling the input of virtual wafers, it can ensure that valuable production capacity is used more efficiently for the processing of actual products while maintaining the stability of the process and the high quality standards of the products. This method not only improves the economy of the production line, but also helps to shorten the production cycle, speed up the time to market, and meet market demand. The objective function is: Min Sum (DummyWaferCount).

[0091] Machine load balancing. All lots are evenly distributed on various machines for processing and production, preventing individual machines from being idle and all lots from being concentrated on only a few machines for production and processing.

[0092] Make as many lots as possible available for processing. Since wafers are expensive and require multiple rounds of complex processing, any delay may cause them to time out in the waiting queue, increasing the risk of scrapping. Therefore, it is crucial to ensure that wafers are processed in a timely manner, which can not only reduce costs, but also improve production efficiency, ensure product quality, and avoid unnecessary economic losses. The objective function is: Max lotPresenceCount.

[0093] In order to cope with the processing needs of multiple batches of wafers (lots) in semiconductor manufacturing plants (fabs), a dynamic priority system is adopted to take into account the differences in delivery deadlines of different batches. This method ensures that high-priority wafer lots can get priority scheduling opportunities, so that they can be successfully completed before the scheduled delivery date to meet customer needs. The objective function is: Min Sum (priority Violation).

[0094] Other indicators required by customers include:

[0095] Each wafer batch (lot) can only select a specific set of equipment for processing during the photolithography process, and the entire process must remain continuous and uninterrupted. Although a batch can be processed on the same set of equipment using different masks, once the processing flow is interrupted, the entire batch of wafers will be scrapped. Therefore, in order to ensure production efficiency and product quality, a set of equipment must be selected for continuous and uninterrupted photolithography processing.

[0096] For lots that need to be grouped, their processing recipes must be the same. And the start and end processing times of the same batch of lots are the same when they are processed on the machine. If lots with different recipes are grouped together, the lot will be scrapped.

[0097] There are rules for the number of lots for both batch and bench. In the case of batch, the upper limit of the number of lots depends on the number of loadports on the machine, while in the case of bench, the number of lots is forced to be 2, with the constraint: Sum(lotCount)∈[minlotCount,maxlotCount].

[0098] The number of lots with small pieces in a batch can be limited. If a batch contains lots with small pieces, it will affect the processing time and efficiency. Therefore, the number of lots with small pieces in a batch can be limited according to customer requirements.

[0099] During the diffusion machine processing, the number of lots in a batch must be less than or equal to 150. Therefore, you can choose to enable the constraint based on the machine type: the total number of wafers in the same batch of lots, the constraint is: Sum(WaferCount)<=150.

[0100] For a diffusion machine, a purge is required after processing a few batches. During the purge period, the machine cannot perform production processing. Therefore, you can choose whether to enable this constraint based on the machine type.

[0101] According to the machine characteristics and other batch constraints required by customers in actual production and processing.

[0102] The equipment can only start the production process after reaching the specified permitted processing time. Each equipment is set with a specific permitted processing time. Only when this time condition is met can the wafer lot (Lot) in the production schedule start its processing production. The constraint is: Min (startTimeOfLot) > = availableTimeOfMachine.

[0103] The processing of a lot must strictly follow its scheduled time frame. Specifically, the processing of a lot cannot start before it arrives, and must be completed within its arrival time plus the maximum allowed time limit. The constraint is: arriveTime<=StartTime<=arriveTime+queueTime.

[0104] The running lot and prepare lot are already in the processing flow or have been loaded into the machine. Their processing time and sequence are pre-set and cannot be adjusted.

[0105] In the case of preventive maintenance (PM) or equipment failure (Down), the equipment will be unable to carry out production processing or perform any other operations, resulting in a temporary interruption of the entire production process.

[0106] Super hot lot refers to the wafer batch that customers urgently need, which has the highest priority. When scheduling production, it is necessary to ensure that such batches can enter the processing flow first to ensure that they can complete production quickly.

[0107] like Figure 4 As shown, batch 1 in the production process enters the equipment for processing. During this period, the equipment is in working condition and processes the wafers of batch 1 according to the predetermined processing technology. During this period, the equipment is in full load operation to ensure that the wafer batch is processed according to the set process requirements.

[0108] After completing the processing of batch 1, the equipment entered the PM / Down / Purge stage. PM (preventive maintenance) means that the equipment needs to be regularly maintained and its performance needs to be checked to ensure that it can continue to operate efficiently and stably. Down (downtime) means that if the equipment fails and needs to be repaired during this period, the equipment will temporarily stop operating. Purge (cleaning) means that according to process requirements, the equipment needs to be cleaned after processing a certain number of batches to prevent impurities from contaminating subsequent batches. During this stage, the equipment temporarily stops production until maintenance, repair or cleaning is completed. This stage is critical to the normal operation of the equipment and production quality.

[0109] After completing the PM / Down / Purge phase, the equipment re-enters production and begins processing batch 2. At this point, the equipment continues to perform its scheduled processing tasks and processes the wafers in batch 2 accordingly to ensure that all process steps are completed as required.

[0110] The Gantt chart output by the scheduling model is as follows Figure 5 As shown in the figure, the Gantt chart visually displays the processing progress of each lot through the horizontal timeline. The production tasks corresponding to each lot are represented by strips of different colors on the Gantt chart, and the length of the strip represents the length of time the lot is processed on the equipment. Through this visual method, managers can clearly see the processing schedule, start and end time of each lot, which facilitates overall production scheduling.

[0111] The "batchid" column in the figure indicates the batch group information. Each batch group contains multiple lots, which are combined together for processing according to the same process requirements. Through the batch group method, the Gantt chart can effectively show how multiple lots are processed in batches on the same equipment, which is convenient for equipment management and batch scheduling. The Gantt chart can help managers view the use of equipment, especially the connection between batches. By observing the interval time between different batches, the idle time and utilization rate of the equipment can be judged. In this way, managers can arrange equipment maintenance or cleaning in advance, avoid unnecessary idle time, and improve the efficiency of equipment use.

[0112] Different processing techniques (such as "diff1", "diff2", etc.) are marked in the Gantt chart, corresponding to different processing stages. The progress of each batch at a certain process stage is clearly visible, helping process engineers track the processing status of each batch and ensure that the process flow is carried out smoothly as planned. Through the Gantt chart, managers can compare the planned time and actual progress of the batch in real time. If the progress of a batch is delayed or completed ahead of schedule, the Gantt chart can quickly reflect these changes, making it easier to make corresponding adjustments and optimizations. It can show the situation of multiple batches being carried out at the same time, which is particularly suitable for displaying parallel production scenarios. Through this parallel display, managers can better balance the load of equipment and ensure that multiple equipment can run synchronously without production bottlenecks.

[0113] The core function of the Gantt chart is to display key information such as production progress, batch combination, equipment utilization rate and process flow through an intuitive timeline. This visualization tool helps managers monitor production status in real time, optimize scheduling, and ensure efficient use of equipment and batches.

[0114] It is not difficult to find that in the embodiment of the present application, the production scheduling of wafers takes into account the arrival time of the l ot, the longest waiting time, the priority and other conditions, reduces unnecessary waiting time, avoids overtime waiting, and greatly reduces the wafer scrap rate, so as to improve product quality and material utilization, reduce overall production costs, and shorten production cycles. At the same time, the needs in actual production are also taken into account, and an interface is left at the algorithm level of the scheduling model, so that the scheduling model has the characteristics of universality.

[0115] The step division of the above methods is only for the purpose of clear description. When implemented, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this patent; adding insignificant modifications to the algorithm or process or introducing insignificant designs without changing the core design of the algorithm and process are all within the scope of protection of this patent.

[0116] In addition, some embodiments of the present application also provide an electronic device. The electronic device may be a digital computer in various forms, such as a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, etc. The electronic device may also be a mobile device in various forms, such as a personal digital processing, a cellular phone, a smart phone, a wearable device, and other similar computing devices.

[0117] The electronic device includes: one or more processors; and a memory storing computer program instructions, wherein when the computer program instructions are executed, the processor executes the steps of the method provided in any one or more of the above embodiments. Figure 6An exemplary structural diagram of the electronic device is disclosed. Figure 6 As shown, the electronic device includes: one or more processors 1101, memory 1102, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses, and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some other embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Among them, the components shown in this article, their connections and relationships, and their functions are only used as examples, and are not intended to limit the implementation of the present application described and / or required herein.

[0118] The electronic device may further include: an input device 1103 and an output device 1104. The processor 1101, the memory 1102, the input device 1103 and the output device 1104 may be connected via a bus or other means. Figure 6 The example of connecting through bus is taken in the following.

[0119] The input device 1103 can receive input digital or character information, and generate key signal input related to the user settings and function control of the electronic device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick and other input devices. The output device 1104 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display and a plasma display. In some embodiments, the display device may be a touch screen.

[0120] To provide interaction with a user, the electronic device may be a computer. The computer has: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball), through which the user can provide input to the computer. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0121] In the embodiments of the present application, a computer program / instruction is stored on a computer-readable medium, and when the computer program / instruction is executed by a processor, the steps of the method provided by any one or more of the above embodiments are implemented. The computer-readable medium may be included in the electronic device described in the above embodiments; or it may exist independently without being assembled into the device. The above computer-readable medium carries one or more computer-readable instructions.

[0122] The memory 1102 can be used as a non-transient computer-readable storage medium, which can be used to store non-transient software programs, non-transient computer executable programs and modules. The processor 1101 executes various functional applications and data processing of the server by running the non-transient software programs, instructions and modules stored in the memory 1102, so as to implement the program instructions / modules corresponding to the method provided by any one or more embodiments in the embodiments of the present application.

[0123] The memory 1102 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 1102 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory 1102 may optionally include a memory remotely arranged relative to the processor 1101, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0124] It should be noted that the computer-readable medium described in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device.

[0125] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, modules of programs or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

[0126] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0127] In the above-described embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. For example, it can be implemented by using an application specific integrated circuit (ASIC), a general-purpose computer or any other similar hardware device. In certain embodiments, the software program of the present application can be executed by a processor to implement the above steps or functions. Similarly, the software program of the present application (including relevant data structures) can be stored in a computer-readable recording medium, for example, a RAM memory, a magnetic or optical drive or a floppy disk and similar devices. In addition, some steps or functions of the present application can be implemented by hardware, for example, as a circuit that cooperates with a processor to perform each step or function.

[0128] The computer program product provided in the embodiment of the present application includes one or more computer programs / instructions, and when the computer program / instructions are executed by the processor, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from a computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk (SSD)), etc.

[0129] The flow chart or block diagram in the accompanying drawings shows the possible architecture, function and operation of the equipment, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated system for hardware that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0130] The scope of the present application is defined by the appended claims rather than the above description, and it is intended that all changes that fall within the meaning and scope of the equivalent elements of the claims are included in the present application. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim may also be implemented by one unit or device through software or hardware. The words "first", "second", etc. are only used to distinguish the description, and do not indicate any particular order, nor can they be understood as indicating or implying relative importance.

[0131] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily mention changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims, and the above embodiments should be regarded as exemplary and non-restrictive.

Claims

1. A wafer fab batch production scheduling method, characterized in that: The method comprises: Obtaining wafer batch information, equipment status information, and equipment maintenance information to be processed; Determine an objective function of the scheduling model, wherein the objective function includes minimizing the processing time of the equipment, minimizing the idle time of the equipment, minimizing the use of replacement pieces, equipment load balancing and high priority batches; Determining constraints of the scheduling model, wherein the constraints include a single-equipment continuous processing limit for each wafer batch, a batching requirement based on the same process recipe, and a cleaning requirement after equipment batch processing; According to the wafer batch information to be processed, the equipment status information and the equipment maintenance information, the scheduling model generates a scheduling plan and outputs a Gantt chart.

2. The method according to claim 1, characterized in that The objective function also includes reducing the waiting time of wafer batches.

3. The method according to claim 1, characterized in that The scheduling model dynamically adjusts the schedule based on the priority of the batches to process high-priority wafer batches.

4. The method according to claim 1, characterized in that: The scheduling model adjusts the availability of equipment according to the preventive maintenance and downtime status of the equipment.

5. The method according to claim 1, characterized in that: The cleaning requirements after batch processing of the equipment include: Determine whether to clean the equipment based on the equipment status information and equipment maintenance information. After the batch number of processed wafers exceeds the preset processing times, the equipment is cleaned, and the equipment is unavailable during the cleaning period.

6. The method according to any one of claims 1 to 5, characterized in that: The method is applied to diffusion area equipment and cleaning area equipment, and the scheduling model generates a scheduling plan for wafers in the diffusion area equipment and cleaning area equipment.

7. The method according to claim 1, characterized in that The scheduling model sets a limit on the number of wafers in a batch according to equipment characteristics, and the limit includes an upper limit and a lower limit on the number of wafers in a batch.

8. An electronic device, characterized in that: The electronic device comprises: one or more processors; and A memory storing computer program instructions, which, when executed, cause the processor to perform the steps of the method as claimed in any one of claims 1 to 7.

9. A computer readable medium having a computer program / instructions stored thereon, characterized in that: When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images